SnowdenLee
SnowdenLee
@Ghaleb-alnakhlani As you mentioned you want to train one model for the whole dataset, so the semantics labels should be consistent across the whole dataset not just for one image....
Hi @zengqixun12, may I ask do you still plan to release the code? Thank you :)
Hi, do you know why use_ema is set to False?
Hi @JudgementH , thanks for your reply. When I set enable_xformers_memory_efficient_attention: False, it's still not working. Is it also the case for you? But if I set it to True,...
Hi @helia95 I might met the same issue. My output looks like this. Was yours look similar? 
Hi @mingqiJ did you solve this issue? I have met the same one Thank you